@theronap/agnoclast-mcp@0.9.151
Connect your AI assistant to Cortex — your org's projects, activity, gaps, and directives, scoped to you.
AI Security Review
scanned 25d ago · by lpm-firewall-aiThe package has no install lifecycle hook, and the relevant agent configuration operations are reached through explicit CLI commands. The flagged Antigravity persistence is an inert artifact unless activated later; the inspected code does not load it.
Decision evidence
public snapshot- package.json declares the CLI entrypoint and no install lifecycle hooks.
- Codex and Cursor adapters describe limited, package-specific MCP integration; Cursor capture does not inject prompt context.
- Setup writes the Cortex MCP configuration, while skills target the Claude and Codex skill directories.
- Uninstall filters managed hooks and allow rules for this package’s own tool namespaces.
- Antigravity’s generated launch agent has RunAtLoad false; its adapter says it does not load the agent.
- The CLI dispatcher reaches install and uninstall through explicit subcommands.
Source & flagged code
6 flaggedPackage source references weak cryptographic algorithms.
lib/capture.mjsView on unpkg · L1Findings
Affected versions and remediation
This report applies to @theronap/agnoclast-mcp@0.9.151.
See all versions of @theronap/agnoclast-mcp for other recorded verdicts.
- Review the evidence and your use of @theronap/agnoclast-mcp@0.9.151 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.